SH/stage6alt_eval.json

{
  "acc_norm_sum_gap": -0.06500000000000017,
  "bpt_gap": 0.5943762334589815,
  "corpus": {
    "dataset": "wikitext",
    "name": "wikitext",
    "num_sequences": 64,
    "sequence_length": 2048,
    "split": "test",
    "subset": "wikitext-2-raw-v1"
  },
  "lm_eval": {
    "arc_easy_limit": 100,
    "hellaswag_limit": 200
  },
  "mode": "thermometer",
  "stage": "6alt",
  "student_acc_norm_sum": 1.4249999999999998,
  "student_arc_easy_acc_norm": 0.73,
  "student_bpt": 3.318567814998621,
  "student_hellaswag_acc_norm": 0.695,
  "teacher_acc_norm_sum": 1.49,
  "teacher_arc_easy_acc_norm": 0.75,
  "teacher_bpt": 2.7241915815396394,
  "teacher_cache": {
    "hit": true,
    "key": "1de59f44ecc5909fe27f32a459674bc96f4fa318564914a33e5c3b9a5f500830",
    "path": "/cache/ablations/_shared/thermometer_teacher_cache.json"
  },
  "teacher_hellaswag_acc_norm": 0.74,
  "top1_agreement": 0.7315889000892639
}